[HIVE-15542] NPE in StatsUtils::getColStatistics when all values in DATE column are NULL

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 2.2.0
• Component/s: Statistics
• Hadoop Flags: Reviewed
• Assignee: Rajesh Balamohan
• Reporter: Rajesh Balamohan
• Created: 05/Jan/17 03:10
• Updated: 25/Jul/17 20:04
• Resolved: 05/Jan/17 23:48

Description

Observed the following stacktrace, when all the values are NULL in date column.

2017-01-04T19:10:37,779 ERROR [46f293ab-1516-429d-aaab-4d5818ef8b82 main] ql.Driver: FAILED: NullPointerException null
java.lang.NullPointerException
        at org.apache.hadoop.hive.ql.stats.StatsUtils.getColStatistics(StatsUtils.java:759)
        at org.apache.hadoop.hive.ql.stats.StatsUtils.convertColStats(StatsUtils.java:806)
        at org.apache.hadoop.hive.ql.stats.StatsUtils.getTableColumnStats(StatsUtils.java:792)
        at org.apache.hadoop.hive.ql.stats.StatsUtils.collectStatistics(StatsUtils.java:206)
        at org.apache.hadoop.hive.ql.stats.StatsUtils.collectStatistics(StatsUtils.java:152)
        at org.apache.hadoop.hive.ql.stats.StatsUtils.collectStatistics(StatsUtils.java:140)
        at org.apache.hadoop.hive.ql.optimizer.stats.annotation.StatsRulesProcFactory$TableScanStatsRule.process(StatsRulesProcFactory.java:128)
        at org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher.dispatch(DefaultRuleDispatcher.java:90)
        at org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatchAndReturn(DefaultGraphWalker.java:105)
        at org.apache.hadoop.hive.ql.lib.DefaultGraphWalker.dispatch(DefaultGraphWalker.java:89)
        at org.apache.hadoop.hive.ql.lib.LevelOrderWalker.walk(LevelOrderWalker.java:143)
        at org.apache.hadoop.hive.ql.lib.LevelOrderWalker.startWalking(LevelOrderWalker.java:122)
        at org.apache.hadoop.hive.ql.optimizer.stats.annotation.AnnotateWithStatistics.transform(AnnotateWithStatistics.java:78)
        at org.apache.hadoop.hive.ql.parse.TezCompiler.runStatsAnnotation(TezCompiler.java:260)
        at org.apache.hadoop.hive.ql.parse.TezCompiler.optimizeOperatorPlan(TezCompiler.java:129)
        at org.apache.hadoop.hive.ql.parse.TaskCompiler.compile(TaskCompiler.java:140)
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:11071)
        at org.apache.hadoop.hive.ql.parse.SemanticAnalyzer.analyzeInternal(SemanticAnalyzer.java:10644)
        at org.apache.hadoop.hive.ql.parse.ColumnStatsSemanticAnalyzer.analyze(ColumnStatsSemanticAnalyzer.java:412)
        at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:510)
        at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1302)
        at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1442)
        at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1222)
        at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1212)
        at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:233)
        at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:184)
        at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:400)
        at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:777)
        at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:715)
        at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:642)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:498)
        at org.apache.hadoop.util.RunJar.run(RunJar.java:221)
        at org.apache.hadoop.util.RunJar.main(RunJar.java:136)